전체 검색
AI 모델 84760
- moondream2-finetuneV2↗
zesquirrelnator
- SMD-MiniMax-H3-Ref2VA-8step-ComfyUI↗
zjwfufu
- Qwen3.6-27B-AEON-Ultimate-Uncensored-Text-NVFP4-MTP-XS↗
AEON-7
- smol_llama-220M-GQA-GGUF↗
afrideva
- ZeroSearch_google_v1_Qwen2.5_3B↗
Alibaba-NLP
- Mantella-Skyrim-Llama-3-8B-GGUF↗
art-from-the-machine
- Supertonic-3-CoreML↗
aufklarer
**First-party CoreML export** of Supertonic-3's four non-autoregressive flow-matching graphs, for on-device iOS / Apple Neural Engine. Built by our own pipeline (`speech-models/stmodels`): weights lifted from the `Supertone/supertonic-3` ONNX initializers → PyTorch `nn.Module` → `coremltools` (`mlprogram`, FP32, iOS18+). Text/duration use **fixed T=128** (relpos attention has T-dependent pad widths — pad/segment text to 128); vocoder + vector-estimator use a dynamic latent-length `RangeDim`. The host runs the flow-matching ODE loop (`vector_estimator` ×`total_steps`) — the graphs contain no control flow. Assets to drive them: `tts.json`, `unicode_indexer.json` (G2P-free tokenizer table), `voice_styles/*.json`. > FP32 = parity reference. For **ANE residency**, use the mixed-precision > `Supertonic-3-CoreML-FP16` — vocoder + duration FP16, > text-encoder + vector-estimator FP32; measured transparent at **47–51 dB** mag-STFT SNR.
- Qwen3.8-27B-AWQ-4bit↗
barrydeen
AWQ **W4A16** quantization of `Qwen/Qwen3.8-27B`, produced with llm-compressor in `compressed-tensors` `pack-quantized` format — the best-optimised Marlin path on Ampere (SM 8.6). Qwen3.8-27B is a **hybrid** model. Only **16 of its 64** decoder layers use full attention; the other **48 use Gated DeltaNet** (`linear_attn.*`). Those DeltaNet projections are extremely sensitive to quantization, so they are left at full BF16 precision here, along with the vision tower and the multi-token-prediction head. That means only **256 Linear modules** are quantized — 16 layers × 4 attention projections plus 64 layers × 3 MLP projections — rather than the ~448 you would get by assuming a uniform architecture. Keeping 48 layers of DeltaNet in BF16 costs roughly 7 GB versus builds that quantize everything, and that is the entire difference in file size.
- Hubble-4B-v1-GGUF↗
bartowski
- nvidia_Llama-3.1-8B-UltraLong-1M-Instruct-GGUF↗
bartowski
